ResNet代码注释

  把比赛中用到的resnet的代码注释了一下，方便以后回忆思想，经典操作和熟悉pytorch的api

---

import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
import torch.nn.functional as F

def conv1x1(in_planes,out_planes,stride=1):
    return nn.Conv2d(in_planes,out_planes,kernel_size =1,stride = stride,bias=False)
def conv3x3(in_planes, out_planes, stride=1):
    "3x3 convolution with padding"
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=1, bias=False)

class BasicBlock(nn.Module):
    expansion = 1
    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv1x1(inplanes, planes)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes, stride)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride

# 总结：basicblock大致就是两次卷积+1次残差链接
    def forward(self, x):
        residual = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        if self.downsample is not None:
            residual = self.downsample(x)
        out += residual
        out = self.relu(out)
        return out

class ResNet(nn.Module):

    def __init__(self, block, layers, strides, compress_layer=True):
        self.inplanes = 32
        super(ResNet, self).__init__()
        # Conv2d(): 前两个参数，分别为in_channels=3, out_channels=32
        self.conv1_new = nn.Conv2d(3, 32, kernel_size=3, stride=strides[0], padding=1,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(32)
        self.relu = nn.ReLU(inplace=True)

        # layers = [3, 4, 6, 6, 3]，表示每个layer中block的数量
        self.layer1 = self._make_layer(block, 32, layers[0],stride=strides[1])
        self.layer2 = self._make_layer(block, 64, layers[1], stride=strides[2])
        self.layer3 = self._make_layer(block, 128, layers[2], stride=strides[3])
        self.layer4 = self._make_layer(block, 256, layers[3], stride=strides[4])        
        self.layer5 = self._make_layer(block, 512, layers[4], stride=strides[5])

        self.compress_layer = compress_layer        
        if compress_layer:
            # for handwritten
            self.layer6 = nn.Sequential(
                nn.Conv2d(512, 256, kernel_size=(3, 1), padding=(0, 0), stride=(1, 1)),
                nn.BatchNorm2d(256),
                nn.ReLU(inplace = True))

        # 初始化权重
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()

    def _make_layer(self, block, planes, blocks, stride=1):
        # block：basicblock
        # planes：输出通道数？
        # blocks：block的数量
        # stride：不等于1就改变通道数和图片尺寸大小，使用downsample(1 x 1卷积，>1的stride)实现

        downsample = None
        # 这里block.expansion == 1， self.inplanes = 32
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * block.expansion),
            )

        layers = []
        # 该层中，第一个block可能是downsample的
        layers.append(block(self.inplanes, planes, stride, downsample))
        # 更新输入通道
        self.inplanes = planes * block.expansion
        # 该层中后续几个block正常接入
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes)) # 实际上这里inplanes和planes已经一样了
        return nn.Sequential(*layers)

    def forward(self, x, multiscale = False):
        out_features = []
        # input: (N, C_in=3, H, W)
        # 经Conv2d后output: (N, C_out=32, H_out, W_out)
        x = self.conv1_new(x)
        x = self.bn1(x)
        x = self.relu(x)

        # 这里tmp_shape为(H_out, W_out)
        tmp_shape = x.size()[2:]

        x = self.layer1(x)
        if x.size()[2:] != tmp_shape:
            tmp_shape = x.size()[2:]
            out_features.append(x)
        x = self.layer2(x)
        if x.size()[2:] != tmp_shape:
            tmp_shape = x.size()[2:]
            out_features.append(x)
        x = self.layer3(x)
        if x.size()[2:] != tmp_shape:
            tmp_shape = x.size()[2:]
            out_features.append(x)
        x = self.layer4(x)
        if x.size()[2:] != tmp_shape:
            tmp_shape = x.size()[2:]
            out_features.append(x)
        x = self.layer5(x)
        if not self.compress_layer:
            out_features.append(x)
        else:
            if x.size()[2:] != tmp_shape:
                tmp_shape = x.size()[2:]
                out_features.append(x)
            x = self.layer6(x)
            out_features.append(x)
        return out_features

def resnet45(strides, compress_layer):
    model = ResNet(BasicBlock, [3, 4, 6, 6, 3], strides, compress_layer)
    return model